SuperCon: Supervised Contrastive Learning for Imbalanced Skin Lesion Classification

TL;DR

This paper introduces SuperCon, a two-stage supervised contrastive learning approach that significantly improves skin lesion classification on imbalanced datasets by learning robust feature representations and fine-tuning classifiers.

Contribution

The paper proposes a novel two-stage training strategy, SuperCon, specifically designed to address class imbalance in skin lesion classification tasks.

Findings

SuperCon outperforms existing methods in F1-score and AUC.

The approach achieves state-of-the-art results on benchmark datasets.

Effective handling of severe class imbalance in skin lesion datasets.

Abstract

Convolutional neural networks (CNNs) have achieved great success in skin lesion classification. A balanced dataset is required to train a good model. However, due to the appearance of different skin lesions in practice, severe or even deadliest skin lesion types (e.g., melanoma) naturally have quite small amount represented in a dataset. In that, classification performance degradation occurs widely, it is significantly important to have CNNs that work well on class imbalanced skin lesion image dataset. In this paper, we propose SuperCon, a two-stage training strategy to overcome the class imbalance problem on skin lesion classification. It contains two stages: (i) representation training that tries to learn a feature representation that closely aligned among intra-classes and distantly apart from inter-classes, and (ii) classifier fine-tuning that aims to learn a classifier that correctly predict the label based on the learnt representations. In the experimental evaluation, extensive comparisons have been made among our approach and other existing approaches on skin lesion benchmark datasets. The results show that our two-stage training strategy effectively addresses the class imbalance classification problem, and significantly improves existing works in terms of F1-score and AUC score, resulting in state-of-the-art performance.